Craig Jones

grandcodepope's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in kernels-community/triton_kernels about 14 hours ago

Update build/torch-universal/triton_kernels/target_info.py

6

#7 opened 6 months ago by

KernelMC

New activity in kernels-community/megablocks about 14 hours ago

Update build.toml

3

#4 opened 9 months ago by

ahadnagy

New activity in kernels-community/punica-sgmv about 14 hours ago

F6: chunked multi-segment dispatch produces non-deterministic silent corruption at production scale

3

#3 opened 4 months ago by

alkari33

New activity in kernels-community/metal-flash-sdpa about 14 hours ago

Add flash_attn_with_kvcache paged-decode kernel (port from huggingface/transformers#45977)

1

#4 opened 4 months ago by

ArthurZ

New activity in kernels-community/rotary about 14 hours ago

Add Metal (Apple Silicon) build variants

2

#6 opened 6 months ago by

robtaylor-chipflow

New activity in kernels-community/metal-flash-sdpa about 14 hours ago

[WIP] Add sliding-window attention support to the varlen kernel

5

#5 opened 3 months ago by

ArthurZ

New activity in kernels-community/flash-attn2 about 14 hours ago

`metadata.json` missing required fields on torch 2.7/2.8/2.9 build variants — breaks `kernels>=0.14`

2

#5 opened 4 months ago by

qgallouedec

New activity in kernels-community/paged-attention about 14 hours ago

Update paged-attention-metal/attention/paged_attention.metal

3

#2 opened about 1 year ago by

ArthurZ

New activity in kernels-community/triton-layer-norm about 14 hours ago

Update autotune configuration to avoid crash on AMD devices

2

#2 opened over 1 year ago by

ror

New activity in kernels-community/activation about 14 hours ago

Available methods in a kernel

2

#5 opened 9 months ago by

christopher5106

New activity in kernels-community/flash-attn3 about 14 hours ago

flash-attn 3 support for rtx 5090?

2

#2 opened 8 months ago by

hydraofm0

New activity in microsoft/Phi-3.5-mini-instruct about 14 hours ago

TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

2

#47 opened 3 months ago by

vigneshwar234

New activity in google/gemma-4-31B-it about 14 hours ago

Bug report + proposed fix for chat_template.jinja

👍🔥 2

1

#142 opened about 1 month ago by

Khalidnass

New activity in BAAI/bge-reranker-v2-m3 about 14 hours ago

Add exported onnx model 'model.onnx'

3

#63 opened 11 days ago by

I-Vi

New activity in coqui/XTTS-v2 about 14 hours ago

Request: DOI

4

#148 opened 20 days ago by

Geminiredirect

New activity in sentence-transformers/paraphrase-multilingual-mpnet-base-v2 about 14 hours ago

Add evaluation results for model sentence-transformers/paraphrase-multilingual-mpnet-base-v2 revision 79f2382ceacceacdf38563d7c5d16b9ff8d725d6

3

#16 opened 6 months ago by

Samoed

New activity in BAAI/bge-base-en-v1.5 about 14 hours ago

Internal model structure preview

2

#17 opened 17 days ago by

svetoviz

New activity in BAAI/bge-large-en-v1.5 about 14 hours ago

Internal model structure preview

3

#40 opened 17 days ago by

svetoviz

New activity in Qwen/Qwen2.5-1.5B-Instruct about 14 hours ago

Our most-deployed mobile model — 16.9 t/s on Snapdragon

2

#22 opened 2 months ago by

3morixd

New activity in google/gemma-2-2b-it about 14 hours ago

Request: DOI

3

#82 opened 3 months ago by

kanha077